Add new SentenceTransformer model.
Browse files- README.md +412 -172
- config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -5,36 +5,67 @@ tags:
|
|
| 5 |
- sentence-transformers
|
| 6 |
- sentence-similarity
|
| 7 |
- feature-extraction
|
| 8 |
-
- dataset_size:
|
| 9 |
-
- loss:
|
| 10 |
base_model: nomic-ai/nomic-embed-text-v1.5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
widget:
|
| 12 |
-
- source_sentence: 'search_query:
|
| 13 |
sentences:
|
| 14 |
-
- 'search_query:
|
| 15 |
-
- 'search_query:
|
| 16 |
-
- 'search_query:
|
| 17 |
-
- source_sentence: 'search_query:
|
| 18 |
sentences:
|
| 19 |
-
- 'search_query:
|
| 20 |
-
- 'search_query:
|
| 21 |
-
- 'search_query:
|
| 22 |
-
- source_sentence: 'search_query:
|
| 23 |
sentences:
|
| 24 |
-
- 'search_query:
|
| 25 |
-
- 'search_query:
|
| 26 |
-
- 'search_query:
|
| 27 |
-
- source_sentence: 'search_query:
|
| 28 |
sentences:
|
| 29 |
-
- 'search_query:
|
| 30 |
-
- 'search_query:
|
| 31 |
-
- 'search_query:
|
| 32 |
-
- source_sentence: 'search_query:
|
| 33 |
sentences:
|
| 34 |
-
- 'search_query:
|
| 35 |
-
- 'search_query:
|
| 36 |
-
- 'search_query:
|
| 37 |
pipeline_tag: sentence-similarity
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
---
|
| 39 |
|
| 40 |
# SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
|
|
@@ -86,9 +117,9 @@ from sentence_transformers import SentenceTransformer
|
|
| 86 |
model = SentenceTransformer("sentence_transformers_model_id")
|
| 87 |
# Run inference
|
| 88 |
sentences = [
|
| 89 |
-
'search_query:
|
| 90 |
-
'search_query:
|
| 91 |
-
'search_query:
|
| 92 |
]
|
| 93 |
embeddings = model.encode(sentences)
|
| 94 |
print(embeddings.shape)
|
|
@@ -124,6 +155,22 @@ You can finetune this model on your own dataset.
|
|
| 124 |
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 125 |
-->
|
| 126 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
<!--
|
| 128 |
## Bias, Risks and Limitations
|
| 129 |
|
|
@@ -143,37 +190,63 @@ You can finetune this model on your own dataset.
|
|
| 143 |
#### Unnamed Dataset
|
| 144 |
|
| 145 |
|
| 146 |
-
* Size:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 148 |
* Approximate statistics based on the first 1000 samples:
|
| 149 |
-
| | anchor | positive
|
| 150 |
-
|
| 151 |
-
| type | string | string
|
| 152 |
-
| details | <ul><li>min: 7 tokens</li><li>mean: 12.
|
| 153 |
* Samples:
|
| 154 |
-
| anchor
|
| 155 |
-
|
| 156 |
-
| <code>search_query:
|
| 157 |
-
| <code>search_query:
|
| 158 |
-
| <code>search_query:
|
| 159 |
-
* Loss: [<code>
|
| 160 |
```json
|
| 161 |
-
{
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
), 'temperature': 0.01}
|
| 166 |
```
|
| 167 |
|
| 168 |
### Training Hyperparameters
|
| 169 |
#### Non-Default Hyperparameters
|
| 170 |
|
| 171 |
-
- `
|
| 172 |
-
- `
|
| 173 |
- `learning_rate`: 1e-05
|
| 174 |
- `lr_scheduler_type`: cosine_with_restarts
|
| 175 |
- `warmup_ratio`: 0.1
|
| 176 |
-
- `
|
|
|
|
| 177 |
- `batch_sampler`: no_duplicates
|
| 178 |
|
| 179 |
#### All Hyperparameters
|
|
@@ -182,11 +255,11 @@ You can finetune this model on your own dataset.
|
|
| 182 |
- `overwrite_output_dir`: False
|
| 183 |
- `do_predict`: False
|
| 184 |
- `prediction_loss_only`: True
|
| 185 |
-
- `per_device_train_batch_size`:
|
| 186 |
-
- `per_device_eval_batch_size`:
|
| 187 |
- `per_gpu_train_batch_size`: None
|
| 188 |
- `per_gpu_eval_batch_size`: None
|
| 189 |
-
- `gradient_accumulation_steps`:
|
| 190 |
- `eval_accumulation_steps`: None
|
| 191 |
- `learning_rate`: 1e-05
|
| 192 |
- `weight_decay`: 0.0
|
|
@@ -215,7 +288,7 @@ You can finetune this model on your own dataset.
|
|
| 215 |
- `jit_mode_eval`: False
|
| 216 |
- `use_ipex`: False
|
| 217 |
- `bf16`: False
|
| 218 |
-
- `fp16`:
|
| 219 |
- `fp16_opt_level`: O1
|
| 220 |
- `half_precision_backend`: auto
|
| 221 |
- `bf16_full_eval`: False
|
|
@@ -226,8 +299,8 @@ You can finetune this model on your own dataset.
|
|
| 226 |
- `tpu_num_cores`: None
|
| 227 |
- `tpu_metrics_debug`: False
|
| 228 |
- `debug`: []
|
| 229 |
-
- `dataloader_drop_last`:
|
| 230 |
-
- `dataloader_num_workers`:
|
| 231 |
- `dataloader_prefetch_factor`: None
|
| 232 |
- `past_index`: -1
|
| 233 |
- `disable_tqdm`: False
|
|
@@ -288,128 +361,283 @@ You can finetune this model on your own dataset.
|
|
| 288 |
### Training Logs
|
| 289 |
<details><summary>Click to expand</summary>
|
| 290 |
|
| 291 |
-
| Epoch | Step | Training Loss |
|
| 292 |
-
|
| 293 |
-
| 0.
|
| 294 |
-
| 0.
|
| 295 |
-
| 0.
|
| 296 |
-
| 0.
|
| 297 |
-
| 0.
|
| 298 |
-
| 0.
|
| 299 |
-
| 0.
|
| 300 |
-
| 0.
|
| 301 |
-
| 0.
|
| 302 |
-
| 0.
|
| 303 |
-
| 0.
|
| 304 |
-
| 0.
|
| 305 |
-
| 0.
|
| 306 |
-
| 0.
|
| 307 |
-
| 0.
|
| 308 |
-
| 0.
|
| 309 |
-
| 0.
|
| 310 |
-
| 0.
|
| 311 |
-
| 0.
|
| 312 |
-
| 0.
|
| 313 |
-
| 0.
|
| 314 |
-
| 0.
|
| 315 |
-
| 0.
|
| 316 |
-
| 0.
|
| 317 |
-
| 0.
|
| 318 |
-
| 0.
|
| 319 |
-
| 0.
|
| 320 |
-
| 0.
|
| 321 |
-
| 0.
|
| 322 |
-
| 0.
|
| 323 |
-
| 0.
|
| 324 |
-
| 0.
|
| 325 |
-
| 0.
|
| 326 |
-
| 0.
|
| 327 |
-
| 0.
|
| 328 |
-
| 0.
|
| 329 |
-
| 0.
|
| 330 |
-
| 0.
|
| 331 |
-
| 0.
|
| 332 |
-
| 0.
|
| 333 |
-
| 0.
|
| 334 |
-
| 0.
|
| 335 |
-
| 0.
|
| 336 |
-
| 0.
|
| 337 |
-
| 0.
|
| 338 |
-
| 0.
|
| 339 |
-
| 0.
|
| 340 |
-
| 0.
|
| 341 |
-
| 0.
|
| 342 |
-
| 0.
|
| 343 |
-
| 0.
|
| 344 |
-
| 0.
|
| 345 |
-
| 0.
|
| 346 |
-
| 0.
|
| 347 |
-
| 0.
|
| 348 |
-
| 0.
|
| 349 |
-
| 0.
|
| 350 |
-
| 0.
|
| 351 |
-
| 0.
|
| 352 |
-
| 0.
|
| 353 |
-
| 0.
|
| 354 |
-
| 0.
|
| 355 |
-
| 0.
|
| 356 |
-
| 0.
|
| 357 |
-
| 0.
|
| 358 |
-
| 0.
|
| 359 |
-
| 0.
|
| 360 |
-
| 0.
|
| 361 |
-
| 0.
|
| 362 |
-
| 0.
|
| 363 |
-
| 0.
|
| 364 |
-
| 0.
|
| 365 |
-
| 0.
|
| 366 |
-
| 0.
|
| 367 |
-
| 0.
|
| 368 |
-
| 0.
|
| 369 |
-
| 0.
|
| 370 |
-
| 0.
|
| 371 |
-
| 0.
|
| 372 |
-
| 0.
|
| 373 |
-
| 0.
|
| 374 |
-
| 0.
|
| 375 |
-
| 0.
|
| 376 |
-
| 0.
|
| 377 |
-
| 0.
|
| 378 |
-
| 0.
|
| 379 |
-
| 0.
|
| 380 |
-
| 0.
|
| 381 |
-
| 0.
|
| 382 |
-
| 0.
|
| 383 |
-
| 0.
|
| 384 |
-
| 0.
|
| 385 |
-
| 0.
|
| 386 |
-
| 0.
|
| 387 |
-
| 0.
|
| 388 |
-
| 0.
|
| 389 |
-
| 0.
|
| 390 |
-
| 0.
|
| 391 |
-
| 0.
|
| 392 |
-
| 0.
|
| 393 |
-
| 0.
|
| 394 |
-
| 0.
|
| 395 |
-
| 0.
|
| 396 |
-
| 0.
|
| 397 |
-
| 0.
|
| 398 |
-
| 0.
|
| 399 |
-
| 0.
|
| 400 |
-
| 0.
|
| 401 |
-
| 0.
|
| 402 |
-
| 0.
|
| 403 |
-
| 0.
|
| 404 |
-
| 0.
|
| 405 |
-
| 0.
|
| 406 |
-
| 0.
|
| 407 |
-
| 0.
|
| 408 |
-
| 0.
|
| 409 |
-
| 0.
|
| 410 |
-
| 0.
|
| 411 |
-
| 0.
|
| 412 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 413 |
|
| 414 |
</details>
|
| 415 |
|
|
@@ -439,6 +667,18 @@ You can finetune this model on your own dataset.
|
|
| 439 |
}
|
| 440 |
```
|
| 441 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 442 |
<!--
|
| 443 |
## Glossary
|
| 444 |
|
|
|
|
| 5 |
- sentence-transformers
|
| 6 |
- sentence-similarity
|
| 7 |
- feature-extraction
|
| 8 |
+
- dataset_size:100K<n<1M
|
| 9 |
+
- loss:TripletLoss
|
| 10 |
base_model: nomic-ai/nomic-embed-text-v1.5
|
| 11 |
+
metrics:
|
| 12 |
+
- cosine_accuracy
|
| 13 |
+
- dot_accuracy
|
| 14 |
+
- manhattan_accuracy
|
| 15 |
+
- euclidean_accuracy
|
| 16 |
+
- max_accuracy
|
| 17 |
widget:
|
| 18 |
+
- source_sentence: 'search_query: floral'
|
| 19 |
sentences:
|
| 20 |
+
- 'search_query: hair dryer'
|
| 21 |
+
- 'search_query: leporad tumbler'
|
| 22 |
+
- 'search_query: cerrojo sin cerradura'
|
| 23 |
+
- source_sentence: 'search_query: 赤ワイシャツ'
|
| 24 |
sentences:
|
| 25 |
+
- 'search_query: sワークス ロードシューズ'
|
| 26 |
+
- 'search_query: ropa astronauta'
|
| 27 |
+
- 'search_query: rosa azul preservada'
|
| 28 |
+
- source_sentence: 'search_query: ギター カポ'
|
| 29 |
sentences:
|
| 30 |
+
- 'search_query: カゴバック'
|
| 31 |
+
- 'search_query: midi flowy dress'
|
| 32 |
+
- 'search_query: pesticide sprayer'
|
| 33 |
+
- source_sentence: 'search_query: note 9'
|
| 34 |
sentences:
|
| 35 |
+
- 'search_query: samsung s9'
|
| 36 |
+
- 'search_query: wallflower jeans'
|
| 37 |
+
- 'search_query: 12 pomos sin tornillos'
|
| 38 |
+
- source_sentence: 'search_query: 傘 鬼滅の刃'
|
| 39 |
sentences:
|
| 40 |
+
- 'search_query: ノースフェイス リュック'
|
| 41 |
+
- 'search_query: お札 を 折ら ない ミニ 財布'
|
| 42 |
+
- 'search_query: buffalo plaid earrings'
|
| 43 |
pipeline_tag: sentence-similarity
|
| 44 |
+
model-index:
|
| 45 |
+
- name: SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
|
| 46 |
+
results:
|
| 47 |
+
- task:
|
| 48 |
+
type: triplet
|
| 49 |
+
name: Triplet
|
| 50 |
+
dataset:
|
| 51 |
+
name: triplet esci
|
| 52 |
+
type: triplet-esci
|
| 53 |
+
metrics:
|
| 54 |
+
- type: cosine_accuracy
|
| 55 |
+
value: 0.655
|
| 56 |
+
name: Cosine Accuracy
|
| 57 |
+
- type: dot_accuracy
|
| 58 |
+
value: 0.343
|
| 59 |
+
name: Dot Accuracy
|
| 60 |
+
- type: manhattan_accuracy
|
| 61 |
+
value: 0.657
|
| 62 |
+
name: Manhattan Accuracy
|
| 63 |
+
- type: euclidean_accuracy
|
| 64 |
+
value: 0.656
|
| 65 |
+
name: Euclidean Accuracy
|
| 66 |
+
- type: max_accuracy
|
| 67 |
+
value: 0.657
|
| 68 |
+
name: Max Accuracy
|
| 69 |
---
|
| 70 |
|
| 71 |
# SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
|
|
|
|
| 117 |
model = SentenceTransformer("sentence_transformers_model_id")
|
| 118 |
# Run inference
|
| 119 |
sentences = [
|
| 120 |
+
'search_query: 傘 鬼滅の刃',
|
| 121 |
+
'search_query: ノースフェイス リュック',
|
| 122 |
+
'search_query: お札 を 折ら ない ミニ 財布',
|
| 123 |
]
|
| 124 |
embeddings = model.encode(sentences)
|
| 125 |
print(embeddings.shape)
|
|
|
|
| 155 |
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 156 |
-->
|
| 157 |
|
| 158 |
+
## Evaluation
|
| 159 |
+
|
| 160 |
+
### Metrics
|
| 161 |
+
|
| 162 |
+
#### Triplet
|
| 163 |
+
* Dataset: `triplet-esci`
|
| 164 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
|
| 165 |
+
|
| 166 |
+
| Metric | Value |
|
| 167 |
+
|:--------------------|:----------|
|
| 168 |
+
| **cosine_accuracy** | **0.655** |
|
| 169 |
+
| dot_accuracy | 0.343 |
|
| 170 |
+
| manhattan_accuracy | 0.657 |
|
| 171 |
+
| euclidean_accuracy | 0.656 |
|
| 172 |
+
| max_accuracy | 0.657 |
|
| 173 |
+
|
| 174 |
<!--
|
| 175 |
## Bias, Risks and Limitations
|
| 176 |
|
|
|
|
| 190 |
#### Unnamed Dataset
|
| 191 |
|
| 192 |
|
| 193 |
+
* Size: 100,000 training samples
|
| 194 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 195 |
+
* Approximate statistics based on the first 1000 samples:
|
| 196 |
+
| | anchor | positive | negative |
|
| 197 |
+
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
|
| 198 |
+
| type | string | string | string |
|
| 199 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 12.21 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 51.18 tokens</li><li>max: 209 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 52.69 tokens</li><li>max: 175 tokens</li></ul> |
|
| 200 |
+
* Samples:
|
| 201 |
+
| anchor | positive | negative |
|
| 202 |
+
|:-----------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 203 |
+
| <code>search_query: college cactus backpack</code> | <code>search_document: Teecho Waterproof Cute Backpack for Girl Casual Print School Bag Women Laptop Backpack Cactus, Teecho, Cactus</code> | <code>search_document: JanSport Huntington Backpack - Lightweight Laptop Bag | Edo Floral, JanSport, Edo Floral</code> |
|
| 204 |
+
| <code>search_query: yellow laces for sneakers</code> | <code>search_document: DELELE Solid Flat Shoelaces Hollow Thick Athletic Shoe Laces Strings Light Yellow 2 Pair 63", DELELE, 05 Light Yellow</code> | <code>search_document: Marrywindix 29 Pairs 47" Flat Colourful Athletic Shoe Laces for Sneakers Skate Shoes Boots Sport Shoes (29 Colors), Marrywindix, Colorful</code> |
|
| 205 |
+
| <code>search_query: home sign grey</code> | <code>search_document: Bigtime Signs Home Sweet Home Sign - 11.75 inch x 9 inch Rigid PVC Signs Decor - Printed Rustic Wood LOOK - Predrilled Hole for Easy Hanging - Family Decoration for Home, Door, Mantle, Porch, Bigtime Signs, Home Sweet Home</code> | <code>search_document: Yankario Funny Bathroom Wall Decor Sign, Farmhouse Rustic Bathroom Decorations Wall Art , 12" by 6" Best Seat Wood Plaque, Yankario, grey 1</code> |
|
| 206 |
+
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
|
| 207 |
+
```json
|
| 208 |
+
{
|
| 209 |
+
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
|
| 210 |
+
"triplet_margin": 5
|
| 211 |
+
}
|
| 212 |
+
```
|
| 213 |
+
|
| 214 |
+
### Evaluation Dataset
|
| 215 |
+
|
| 216 |
+
#### Unnamed Dataset
|
| 217 |
+
|
| 218 |
+
|
| 219 |
+
* Size: 1,000 evaluation samples
|
| 220 |
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 221 |
* Approximate statistics based on the first 1000 samples:
|
| 222 |
+
| | anchor | positive | negative |
|
| 223 |
+
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
|
| 224 |
+
| type | string | string | string |
|
| 225 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 12.24 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 53.16 tokens</li><li>max: 173 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 53.72 tokens</li><li>max: 175 tokens</li></ul> |
|
| 226 |
* Samples:
|
| 227 |
+
| anchor | positive | negative |
|
| 228 |
+
|:---------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 229 |
+
| <code>search_query: black vinyl placemat</code> | <code>search_document: Red-A Dining Table Placemats Set of 4 Heat-Resistant Wipeable Table Mats for Kitchen Table Decoration Waterproof Vinyl Placemats Easy to Clean,Black w/Brown, Red-A, Black</code> | <code>search_document: Winknowl Placemats, Set of 8 Heat Resistant Stain Resistant Non-Slip Woven Vinyl Insulation Placemats, Washable Durable Elegant Table Mats for Dining (Black), Winknowl, Black</code> |
|
| 230 |
+
| <code>search_query: 1 1/2 leather belts without buckle</code> | <code>search_document: Vatee's Women's/Men's Real Leather Replacement Belt Strap No Buckle 1 1/2"(38mm) Wide 45" Long Black, Vatee's, 154: Black</code> | <code>search_document: Women Skinny Leather Belt Thin Waist Jeans Belt for Pants in Pin Buckle Belt by WHIPPY, Black/Brown, Suit Pants 24-29 Inches, WHIPPY, 2-black+brown</code> |
|
| 231 |
+
| <code>search_query: 1x cat 7a conector de red rj45 sin herramientas</code> | <code>search_document: deleyCON 3,0m RJ45 Cable Plano Cable de Red de Categoría CAT7 Cable Ethernet U/FTP con Revestimiento Interior de Cobre - Negro, deleyCON, Negro</code> | <code>search_document: Conector de Odedo®, 2 unidades, categoría 6, UTP RJ45, para cable de conexión, prolongación de 6,3 mm, AWG 23-26 montaje sin herramientas, contactos dorados, odedo, Weiß</code> |
|
| 232 |
+
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
|
| 233 |
```json
|
| 234 |
+
{
|
| 235 |
+
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
|
| 236 |
+
"triplet_margin": 5
|
| 237 |
+
}
|
|
|
|
| 238 |
```
|
| 239 |
|
| 240 |
### Training Hyperparameters
|
| 241 |
#### Non-Default Hyperparameters
|
| 242 |
|
| 243 |
+
- `per_device_train_batch_size`: 4
|
| 244 |
+
- `per_device_eval_batch_size`: 4
|
| 245 |
- `learning_rate`: 1e-05
|
| 246 |
- `lr_scheduler_type`: cosine_with_restarts
|
| 247 |
- `warmup_ratio`: 0.1
|
| 248 |
+
- `dataloader_drop_last`: True
|
| 249 |
+
- `dataloader_num_workers`: 4
|
| 250 |
- `batch_sampler`: no_duplicates
|
| 251 |
|
| 252 |
#### All Hyperparameters
|
|
|
|
| 255 |
- `overwrite_output_dir`: False
|
| 256 |
- `do_predict`: False
|
| 257 |
- `prediction_loss_only`: True
|
| 258 |
+
- `per_device_train_batch_size`: 4
|
| 259 |
+
- `per_device_eval_batch_size`: 4
|
| 260 |
- `per_gpu_train_batch_size`: None
|
| 261 |
- `per_gpu_eval_batch_size`: None
|
| 262 |
+
- `gradient_accumulation_steps`: 1
|
| 263 |
- `eval_accumulation_steps`: None
|
| 264 |
- `learning_rate`: 1e-05
|
| 265 |
- `weight_decay`: 0.0
|
|
|
|
| 288 |
- `jit_mode_eval`: False
|
| 289 |
- `use_ipex`: False
|
| 290 |
- `bf16`: False
|
| 291 |
+
- `fp16`: False
|
| 292 |
- `fp16_opt_level`: O1
|
| 293 |
- `half_precision_backend`: auto
|
| 294 |
- `bf16_full_eval`: False
|
|
|
|
| 299 |
- `tpu_num_cores`: None
|
| 300 |
- `tpu_metrics_debug`: False
|
| 301 |
- `debug`: []
|
| 302 |
+
- `dataloader_drop_last`: True
|
| 303 |
+
- `dataloader_num_workers`: 4
|
| 304 |
- `dataloader_prefetch_factor`: None
|
| 305 |
- `past_index`: -1
|
| 306 |
- `disable_tqdm`: False
|
|
|
|
| 361 |
### Training Logs
|
| 362 |
<details><summary>Click to expand</summary>
|
| 363 |
|
| 364 |
+
| Epoch | Step | Training Loss | loss | triplet-esci_cosine_accuracy |
|
| 365 |
+
|:------:|:-----:|:-------------:|:------:|:----------------------------:|
|
| 366 |
+
| 0.008 | 200 | 3.9805 | - | - |
|
| 367 |
+
| 0.016 | 400 | 4.0739 | - | - |
|
| 368 |
+
| 0.024 | 600 | 4.0571 | - | - |
|
| 369 |
+
| 0.032 | 800 | 3.8848 | - | - |
|
| 370 |
+
| 0.04 | 1000 | 3.8249 | 3.9825 | 0.664 |
|
| 371 |
+
| 0.048 | 1200 | 3.7097 | - | - |
|
| 372 |
+
| 0.056 | 1400 | 3.6869 | - | - |
|
| 373 |
+
| 0.064 | 1600 | 3.4327 | - | - |
|
| 374 |
+
| 0.072 | 1800 | 3.64 | - | - |
|
| 375 |
+
| 0.08 | 2000 | 3.3813 | 3.8244 | 0.657 |
|
| 376 |
+
| 0.088 | 2200 | 3.4011 | - | - |
|
| 377 |
+
| 0.096 | 2400 | 3.34 | - | - |
|
| 378 |
+
| 0.104 | 2600 | 3.2488 | - | - |
|
| 379 |
+
| 0.112 | 2800 | 3.5031 | - | - |
|
| 380 |
+
| 0.12 | 3000 | 3.3615 | 3.7263 | 0.674 |
|
| 381 |
+
| 0.128 | 3200 | 3.1028 | - | - |
|
| 382 |
+
| 0.136 | 3400 | 3.2969 | - | - |
|
| 383 |
+
| 0.144 | 3600 | 3.0463 | - | - |
|
| 384 |
+
| 0.152 | 3800 | 3.1194 | - | - |
|
| 385 |
+
| 0.16 | 4000 | 3.2372 | 3.6599 | 0.673 |
|
| 386 |
+
| 0.168 | 4200 | 3.2954 | - | - |
|
| 387 |
+
| 0.176 | 4400 | 3.2753 | - | - |
|
| 388 |
+
| 0.184 | 4600 | 3.179 | - | - |
|
| 389 |
+
| 0.192 | 4800 | 3.2646 | - | - |
|
| 390 |
+
| 0.2 | 5000 | 3.1295 | 3.6405 | 0.677 |
|
| 391 |
+
| 0.208 | 5200 | 3.2211 | - | - |
|
| 392 |
+
| 0.216 | 5400 | 3.2222 | - | - |
|
| 393 |
+
| 0.224 | 5600 | 2.9471 | - | - |
|
| 394 |
+
| 0.232 | 5800 | 3.1564 | - | - |
|
| 395 |
+
| 0.24 | 6000 | 3.1099 | 3.6138 | 0.684 |
|
| 396 |
+
| 0.248 | 6200 | 2.9399 | - | - |
|
| 397 |
+
| 0.256 | 6400 | 3.1087 | - | - |
|
| 398 |
+
| 0.264 | 6600 | 3.2675 | - | - |
|
| 399 |
+
| 0.272 | 6800 | 3.2149 | - | - |
|
| 400 |
+
| 0.28 | 7000 | 2.9484 | 3.6086 | 0.673 |
|
| 401 |
+
| 0.288 | 7200 | 3.0829 | - | - |
|
| 402 |
+
| 0.296 | 7400 | 3.1864 | - | - |
|
| 403 |
+
| 0.304 | 7600 | 3.1201 | - | - |
|
| 404 |
+
| 0.312 | 7800 | 3.0698 | - | - |
|
| 405 |
+
| 0.32 | 8000 | 2.9968 | 3.5750 | 0.668 |
|
| 406 |
+
| 0.328 | 8200 | 3.0636 | - | - |
|
| 407 |
+
| 0.336 | 8400 | 3.1293 | - | - |
|
| 408 |
+
| 0.344 | 8600 | 3.1282 | - | - |
|
| 409 |
+
| 0.352 | 8800 | 3.1415 | - | - |
|
| 410 |
+
| 0.36 | 9000 | 2.7868 | 3.5211 | 0.693 |
|
| 411 |
+
| 0.368 | 9200 | 2.9714 | - | - |
|
| 412 |
+
| 0.376 | 9400 | 2.9409 | - | - |
|
| 413 |
+
| 0.384 | 9600 | 2.9071 | - | - |
|
| 414 |
+
| 0.392 | 9800 | 2.9154 | - | - |
|
| 415 |
+
| 0.4 | 10000 | 2.9709 | 3.5510 | 0.683 |
|
| 416 |
+
| 0.408 | 10200 | 2.741 | - | - |
|
| 417 |
+
| 0.416 | 10400 | 2.678 | - | - |
|
| 418 |
+
| 0.424 | 10600 | 2.8429 | - | - |
|
| 419 |
+
| 0.432 | 10800 | 2.9782 | - | - |
|
| 420 |
+
| 0.44 | 11000 | 2.9548 | 3.5369 | 0.681 |
|
| 421 |
+
| 0.448 | 11200 | 2.8452 | - | - |
|
| 422 |
+
| 0.456 | 11400 | 2.8578 | - | - |
|
| 423 |
+
| 0.464 | 11600 | 2.9211 | - | - |
|
| 424 |
+
| 0.472 | 11800 | 2.897 | - | - |
|
| 425 |
+
| 0.48 | 12000 | 2.7651 | 3.6031 | 0.687 |
|
| 426 |
+
| 0.488 | 12200 | 2.9472 | - | - |
|
| 427 |
+
| 0.496 | 12400 | 2.6198 | - | - |
|
| 428 |
+
| 0.504 | 12600 | 2.8444 | - | - |
|
| 429 |
+
| 0.512 | 12800 | 2.7384 | - | - |
|
| 430 |
+
| 0.52 | 13000 | 2.7827 | 3.6082 | 0.68 |
|
| 431 |
+
| 0.528 | 13200 | 2.6882 | - | - |
|
| 432 |
+
| 0.536 | 13400 | 2.6722 | - | - |
|
| 433 |
+
| 0.544 | 13600 | 2.7218 | - | - |
|
| 434 |
+
| 0.552 | 13800 | 2.7278 | - | - |
|
| 435 |
+
| 0.56 | 14000 | 2.7156 | 3.5606 | 0.677 |
|
| 436 |
+
| 0.568 | 14200 | 2.5748 | - | - |
|
| 437 |
+
| 0.576 | 14400 | 2.5414 | - | - |
|
| 438 |
+
| 0.584 | 14600 | 2.6918 | - | - |
|
| 439 |
+
| 0.592 | 14800 | 2.5429 | - | - |
|
| 440 |
+
| 0.6 | 15000 | 2.5724 | 3.5178 | 0.694 |
|
| 441 |
+
| 0.608 | 15200 | 2.7594 | - | - |
|
| 442 |
+
| 0.616 | 15400 | 2.4841 | - | - |
|
| 443 |
+
| 0.624 | 15600 | 2.4667 | - | - |
|
| 444 |
+
| 0.632 | 15800 | 2.6253 | - | - |
|
| 445 |
+
| 0.64 | 16000 | 2.5001 | 3.5428 | 0.683 |
|
| 446 |
+
| 0.648 | 16200 | 2.5707 | - | - |
|
| 447 |
+
| 0.656 | 16400 | 2.4924 | - | - |
|
| 448 |
+
| 0.664 | 16600 | 2.5419 | - | - |
|
| 449 |
+
| 0.672 | 16800 | 2.487 | - | - |
|
| 450 |
+
| 0.68 | 17000 | 2.4747 | 3.5825 | 0.681 |
|
| 451 |
+
| 0.688 | 17200 | 2.4194 | - | - |
|
| 452 |
+
| 0.696 | 17400 | 2.5714 | - | - |
|
| 453 |
+
| 0.704 | 17600 | 2.4069 | - | - |
|
| 454 |
+
| 0.712 | 17800 | 2.5767 | - | - |
|
| 455 |
+
| 0.72 | 18000 | 2.5952 | 3.6268 | 0.684 |
|
| 456 |
+
| 0.728 | 18200 | 2.4023 | - | - |
|
| 457 |
+
| 0.736 | 18400 | 2.3989 | - | - |
|
| 458 |
+
| 0.744 | 18600 | 2.379 | - | - |
|
| 459 |
+
| 0.752 | 18800 | 2.4943 | - | - |
|
| 460 |
+
| 0.76 | 19000 | 2.3762 | 3.5686 | 0.701 |
|
| 461 |
+
| 0.768 | 19200 | 2.4825 | - | - |
|
| 462 |
+
| 0.776 | 19400 | 2.4451 | - | - |
|
| 463 |
+
| 0.784 | 19600 | 2.5374 | - | - |
|
| 464 |
+
| 0.792 | 19800 | 2.4569 | - | - |
|
| 465 |
+
| 0.8 | 20000 | 2.2353 | 3.6429 | 0.681 |
|
| 466 |
+
| 0.808 | 20200 | 2.3447 | - | - |
|
| 467 |
+
| 0.816 | 20400 | 2.3083 | - | - |
|
| 468 |
+
| 0.824 | 20600 | 2.2126 | - | - |
|
| 469 |
+
| 0.832 | 20800 | 2.3935 | - | - |
|
| 470 |
+
| 0.84 | 21000 | 2.5115 | 3.6387 | 0.68 |
|
| 471 |
+
| 0.848 | 21200 | 2.1469 | - | - |
|
| 472 |
+
| 0.856 | 21400 | 2.2717 | - | - |
|
| 473 |
+
| 0.864 | 21600 | 2.2993 | - | - |
|
| 474 |
+
| 0.872 | 21800 | 2.3519 | - | - |
|
| 475 |
+
| 0.88 | 22000 | 2.2947 | 3.5908 | 0.671 |
|
| 476 |
+
| 0.888 | 22200 | 2.3249 | - | - |
|
| 477 |
+
| 0.896 | 22400 | 2.2452 | - | - |
|
| 478 |
+
| 0.904 | 22600 | 2.114 | - | - |
|
| 479 |
+
| 0.912 | 22800 | 2.208 | - | - |
|
| 480 |
+
| 0.92 | 23000 | 2.4168 | 3.6659 | 0.671 |
|
| 481 |
+
| 0.928 | 23200 | 2.2098 | - | - |
|
| 482 |
+
| 0.936 | 23400 | 2.1805 | - | - |
|
| 483 |
+
| 0.944 | 23600 | 2.122 | - | - |
|
| 484 |
+
| 0.952 | 23800 | 2.1364 | - | - |
|
| 485 |
+
| 0.96 | 24000 | 2.1464 | 3.6284 | 0.671 |
|
| 486 |
+
| 0.968 | 24200 | 2.1298 | - | - |
|
| 487 |
+
| 0.976 | 24400 | 2.2657 | - | - |
|
| 488 |
+
| 0.984 | 24600 | 2.304 | - | - |
|
| 489 |
+
| 0.992 | 24800 | 2.175 | - | - |
|
| 490 |
+
| 1.0 | 25000 | 2.1349 | 3.6532 | 0.681 |
|
| 491 |
+
| 1.008 | 25200 | 2.0151 | - | - |
|
| 492 |
+
| 1.016 | 25400 | 2.0881 | - | - |
|
| 493 |
+
| 1.024 | 25600 | 1.9897 | - | - |
|
| 494 |
+
| 1.032 | 25800 | 2.1987 | - | - |
|
| 495 |
+
| 1.04 | 26000 | 1.9913 | 3.6511 | 0.672 |
|
| 496 |
+
| 1.048 | 26200 | 1.9088 | - | - |
|
| 497 |
+
| 1.056 | 26400 | 1.9555 | - | - |
|
| 498 |
+
| 1.064 | 26600 | 1.6892 | - | - |
|
| 499 |
+
| 1.072 | 26800 | 2.0404 | - | - |
|
| 500 |
+
| 1.08 | 27000 | 1.6976 | 3.6465 | 0.671 |
|
| 501 |
+
| 1.088 | 27200 | 1.894 | - | - |
|
| 502 |
+
| 1.096 | 27400 | 1.8056 | - | - |
|
| 503 |
+
| 1.104 | 27600 | 1.6426 | - | - |
|
| 504 |
+
| 1.112 | 27800 | 2.0203 | - | - |
|
| 505 |
+
| 1.12 | 28000 | 1.697 | 3.6182 | 0.681 |
|
| 506 |
+
| 1.1280 | 28200 | 1.5562 | - | - |
|
| 507 |
+
| 1.1360 | 28400 | 1.6061 | - | - |
|
| 508 |
+
| 1.144 | 28600 | 1.5201 | - | - |
|
| 509 |
+
| 1.152 | 28800 | 1.4388 | - | - |
|
| 510 |
+
| 1.16 | 29000 | 1.5198 | 3.5924 | 0.676 |
|
| 511 |
+
| 1.168 | 29200 | 1.6404 | - | - |
|
| 512 |
+
| 1.176 | 29400 | 1.6058 | - | - |
|
| 513 |
+
| 1.184 | 29600 | 1.6063 | - | - |
|
| 514 |
+
| 1.192 | 29800 | 1.4398 | - | - |
|
| 515 |
+
| 1.2 | 30000 | 1.4952 | 3.6587 | 0.665 |
|
| 516 |
+
| 1.208 | 30200 | 1.5077 | - | - |
|
| 517 |
+
| 1.216 | 30400 | 1.3177 | - | - |
|
| 518 |
+
| 1.224 | 30600 | 1.095 | - | - |
|
| 519 |
+
| 1.232 | 30800 | 1.2841 | - | - |
|
| 520 |
+
| 1.24 | 31000 | 1.3544 | 3.6066 | 0.684 |
|
| 521 |
+
| 1.248 | 31200 | 1.2188 | - | - |
|
| 522 |
+
| 1.256 | 31400 | 1.1761 | - | - |
|
| 523 |
+
| 1.264 | 31600 | 1.2601 | - | - |
|
| 524 |
+
| 1.272 | 31800 | 1.2057 | - | - |
|
| 525 |
+
| 1.28 | 32000 | 1.0478 | 3.6371 | 0.681 |
|
| 526 |
+
| 1.288 | 32200 | 1.0888 | - | - |
|
| 527 |
+
| 1.296 | 32400 | 1.1335 | - | - |
|
| 528 |
+
| 1.304 | 32600 | 1.1297 | - | - |
|
| 529 |
+
| 1.312 | 32800 | 1.0302 | - | - |
|
| 530 |
+
| 1.32 | 33000 | 1.0583 | 3.6186 | 0.685 |
|
| 531 |
+
| 1.328 | 33200 | 1.0623 | - | - |
|
| 532 |
+
| 1.336 | 33400 | 0.9047 | - | - |
|
| 533 |
+
| 1.3440 | 33600 | 1.0706 | - | - |
|
| 534 |
+
| 1.3520 | 33800 | 1.0877 | - | - |
|
| 535 |
+
| 1.3600 | 34000 | 0.8205 | 3.6613 | 0.653 |
|
| 536 |
+
| 1.3680 | 34200 | 0.9596 | - | - |
|
| 537 |
+
| 1.376 | 34400 | 0.8855 | - | - |
|
| 538 |
+
| 1.384 | 34600 | 0.9186 | - | - |
|
| 539 |
+
| 1.392 | 34800 | 0.8087 | - | - |
|
| 540 |
+
| 1.4 | 35000 | 0.9732 | 3.6558 | 0.662 |
|
| 541 |
+
| 1.408 | 35200 | 0.8753 | - | - |
|
| 542 |
+
| 1.416 | 35400 | 0.8257 | - | - |
|
| 543 |
+
| 1.424 | 35600 | 0.8689 | - | - |
|
| 544 |
+
| 1.432 | 35800 | 0.8596 | - | - |
|
| 545 |
+
| 1.44 | 36000 | 0.9202 | 3.6872 | 0.66 |
|
| 546 |
+
| 1.448 | 36200 | 0.8993 | - | - |
|
| 547 |
+
| 1.456 | 36400 | 0.8889 | - | - |
|
| 548 |
+
| 1.464 | 36600 | 0.9138 | - | - |
|
| 549 |
+
| 1.472 | 36800 | 0.8212 | - | - |
|
| 550 |
+
| 1.48 | 37000 | 0.7591 | 3.6708 | 0.666 |
|
| 551 |
+
| 1.488 | 37200 | 0.769 | - | - |
|
| 552 |
+
| 1.496 | 37400 | 0.8656 | - | - |
|
| 553 |
+
| 1.504 | 37600 | 0.9134 | - | - |
|
| 554 |
+
| 1.512 | 37800 | 0.7212 | - | - |
|
| 555 |
+
| 1.52 | 38000 | 0.8118 | 3.6249 | 0.672 |
|
| 556 |
+
| 1.528 | 38200 | 0.7454 | - | - |
|
| 557 |
+
| 1.536 | 38400 | 0.7491 | - | - |
|
| 558 |
+
| 1.544 | 38600 | 0.8148 | - | - |
|
| 559 |
+
| 1.552 | 38800 | 0.6845 | - | - |
|
| 560 |
+
| 1.56 | 39000 | 0.6169 | 3.6868 | 0.679 |
|
| 561 |
+
| 1.568 | 39200 | 0.7377 | - | - |
|
| 562 |
+
| 1.576 | 39400 | 0.7296 | - | - |
|
| 563 |
+
| 1.584 | 39600 | 0.7204 | - | - |
|
| 564 |
+
| 1.592 | 39800 | 0.6748 | - | - |
|
| 565 |
+
| 1.6 | 40000 | 0.6494 | 3.7054 | 0.673 |
|
| 566 |
+
| 1.608 | 40200 | 0.7435 | - | - |
|
| 567 |
+
| 1.616 | 40400 | 0.6196 | - | - |
|
| 568 |
+
| 1.624 | 40600 | 0.6977 | - | - |
|
| 569 |
+
| 1.6320 | 40800 | 0.7442 | - | - |
|
| 570 |
+
| 1.6400 | 41000 | 0.5824 | 3.7500 | 0.66 |
|
| 571 |
+
| 1.6480 | 41200 | 0.6144 | - | - |
|
| 572 |
+
| 1.6560 | 41400 | 0.5909 | - | - |
|
| 573 |
+
| 1.6640 | 41600 | 0.6717 | - | - |
|
| 574 |
+
| 1.6720 | 41800 | 0.6436 | - | - |
|
| 575 |
+
| 1.6800 | 42000 | 0.6161 | 3.6769 | 0.676 |
|
| 576 |
+
| 1.688 | 42200 | 0.5282 | - | - |
|
| 577 |
+
| 1.696 | 42400 | 0.6647 | - | - |
|
| 578 |
+
| 1.704 | 42600 | 0.649 | - | - |
|
| 579 |
+
| 1.712 | 42800 | 0.6284 | - | - |
|
| 580 |
+
| 1.72 | 43000 | 0.7055 | 3.6992 | 0.671 |
|
| 581 |
+
| 1.728 | 43200 | 0.6249 | - | - |
|
| 582 |
+
| 1.736 | 43400 | 0.5722 | - | - |
|
| 583 |
+
| 1.744 | 43600 | 0.621 | - | - |
|
| 584 |
+
| 1.752 | 43800 | 0.6129 | - | - |
|
| 585 |
+
| 1.76 | 44000 | 0.501 | 3.7589 | 0.662 |
|
| 586 |
+
| 1.768 | 44200 | 0.5566 | - | - |
|
| 587 |
+
| 1.776 | 44400 | 0.576 | - | - |
|
| 588 |
+
| 1.784 | 44600 | 0.6428 | - | - |
|
| 589 |
+
| 1.792 | 44800 | 0.5629 | - | - |
|
| 590 |
+
| 1.8 | 45000 | 0.5134 | 3.7530 | 0.659 |
|
| 591 |
+
| 1.808 | 45200 | 0.4681 | - | - |
|
| 592 |
+
| 1.8160 | 45400 | 0.6268 | - | - |
|
| 593 |
+
| 1.8240 | 45600 | 0.5877 | - | - |
|
| 594 |
+
| 1.8320 | 45800 | 0.5219 | - | - |
|
| 595 |
+
| 1.8400 | 46000 | 0.545 | 3.7755 | 0.658 |
|
| 596 |
+
| 1.8480 | 46200 | 0.4539 | - | - |
|
| 597 |
+
| 1.8560 | 46400 | 0.5255 | - | - |
|
| 598 |
+
| 1.8640 | 46600 | 0.5573 | - | - |
|
| 599 |
+
| 1.8720 | 46800 | 0.5508 | - | - |
|
| 600 |
+
| 1.88 | 47000 | 0.5391 | 3.7489 | 0.653 |
|
| 601 |
+
| 1.888 | 47200 | 0.4276 | - | - |
|
| 602 |
+
| 1.896 | 47400 | 0.4906 | - | - |
|
| 603 |
+
| 1.904 | 47600 | 0.3771 | - | - |
|
| 604 |
+
| 1.912 | 47800 | 0.4959 | - | - |
|
| 605 |
+
| 1.92 | 48000 | 0.5377 | 3.7770 | 0.658 |
|
| 606 |
+
| 1.928 | 48200 | 0.4807 | - | - |
|
| 607 |
+
| 1.936 | 48400 | 0.5239 | - | - |
|
| 608 |
+
| 1.944 | 48600 | 0.4441 | - | - |
|
| 609 |
+
| 1.952 | 48800 | 0.4536 | - | - |
|
| 610 |
+
| 1.96 | 49000 | 0.5265 | 3.7507 | 0.669 |
|
| 611 |
+
| 1.968 | 49200 | 0.3817 | - | - |
|
| 612 |
+
| 1.976 | 49400 | 0.4468 | - | - |
|
| 613 |
+
| 1.984 | 49600 | 0.5766 | - | - |
|
| 614 |
+
| 1.992 | 49800 | 0.4789 | - | - |
|
| 615 |
+
| 2.0 | 50000 | 0.4853 | 3.7328 | 0.663 |
|
| 616 |
+
| 2.008 | 50200 | 0.3744 | - | - |
|
| 617 |
+
| 2.016 | 50400 | 0.4662 | - | - |
|
| 618 |
+
| 2.024 | 50600 | 0.394 | - | - |
|
| 619 |
+
| 2.032 | 50800 | 0.3938 | - | - |
|
| 620 |
+
| 2.04 | 51000 | 0.3586 | 3.8004 | 0.656 |
|
| 621 |
+
| 2.048 | 51200 | 0.3522 | - | - |
|
| 622 |
+
| 2.056 | 51400 | 0.4173 | - | - |
|
| 623 |
+
| 2.064 | 51600 | 0.3177 | - | - |
|
| 624 |
+
| 2.072 | 51800 | 0.4113 | - | - |
|
| 625 |
+
| 2.08 | 52000 | 0.3027 | 3.7366 | 0.665 |
|
| 626 |
+
| 2.088 | 52200 | 0.3693 | - | - |
|
| 627 |
+
| 2.096 | 52400 | 0.4268 | - | - |
|
| 628 |
+
| 2.104 | 52600 | 0.3678 | - | - |
|
| 629 |
+
| 2.112 | 52800 | 0.4192 | - | - |
|
| 630 |
+
| 2.12 | 53000 | 0.3105 | 3.7831 | 0.661 |
|
| 631 |
+
| 2.128 | 53200 | 0.3228 | - | - |
|
| 632 |
+
| 2.136 | 53400 | 0.2408 | - | - |
|
| 633 |
+
| 2.144 | 53600 | 0.2804 | - | - |
|
| 634 |
+
| 2.152 | 53800 | 0.3034 | - | - |
|
| 635 |
+
| 2.16 | 54000 | 0.3562 | 3.7866 | 0.656 |
|
| 636 |
+
| 2.168 | 54200 | 0.3526 | - | - |
|
| 637 |
+
| 2.176 | 54400 | 0.414 | - | - |
|
| 638 |
+
| 2.184 | 54600 | 0.3678 | - | - |
|
| 639 |
+
| 2.192 | 54800 | 0.2965 | - | - |
|
| 640 |
+
| 2.2 | 55000 | 0.3691 | 3.8108 | 0.655 |
|
| 641 |
|
| 642 |
</details>
|
| 643 |
|
|
|
|
| 667 |
}
|
| 668 |
```
|
| 669 |
|
| 670 |
+
#### TripletLoss
|
| 671 |
+
```bibtex
|
| 672 |
+
@misc{hermans2017defense,
|
| 673 |
+
title={In Defense of the Triplet Loss for Person Re-Identification},
|
| 674 |
+
author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
|
| 675 |
+
year={2017},
|
| 676 |
+
eprint={1703.07737},
|
| 677 |
+
archivePrefix={arXiv},
|
| 678 |
+
primaryClass={cs.CV}
|
| 679 |
+
}
|
| 680 |
+
```
|
| 681 |
+
|
| 682 |
<!--
|
| 683 |
## Glossary
|
| 684 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "models/nomic-embed-text-esci/checkpoint-
|
| 3 |
"activation_function": "swiglu",
|
| 4 |
"architectures": [
|
| 5 |
"NomicBertModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "models/nomic-embed-text-esci/checkpoint-55000",
|
| 3 |
"activation_function": "swiglu",
|
| 4 |
"architectures": [
|
| 5 |
"NomicBertModel"
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 546938168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:414b031b610e8f3df6786386dde6ba3ce370027798e807e9e3d93ac4764e355d
|
| 3 |
size 546938168
|